Assessing the Impact of Intercurrent Events on Power and Sample Size for Estimands with Time-to-Event Endpoints

2026-06-02

AI Summary

This study addresses the common oversight in traditional clinical trial sample size calculations—namely, the neglect of intercurrent events (IEs) and their handling strategies’ impact on the target estimand, which can lead to inaccurate power assessments. Focusing on time-to-event trials with fixed follow-up durations, the authors propose, within the ICH E9(R1) framework, the first closed-form power calculation formulas applicable to multiple IE-handling strategies, including treatment, hypothetical, and composite strategies. By employing probabilistic modeling and analytical derivations under the assumption of independence between IEs and the primary endpoint, the method substantially reduces computational complexity while enabling efficient sensitivity analyses. Simulation studies and a real-world nasal polyps case demonstrate the high accuracy of the proposed formulas and reveal that both IE incidence rates and post-IE outcomes significantly influence required sample sizes, thereby supporting estimand-aligned trial design.

Abstract

The precise definition of a primary estimand, accounting for intercurrent events (IEs) as per the ICH E9(R1) addendum, is fundamental to the design and interpretation of clinical trials. Conventional power and sample size calculations, however, often do not adequately incorporate the impact of IEs and their corresponding handling strategies, creating a risk of over- or under-powered studies. While simulation-based approaches can address this complexity, they are often computationally intensive and may only explore a limited set of scenarios. In this paper, we introduce a set of formulae for calculating power for estimands with time-to-event endpoints, applied to trials with fixed follow-up durations. We focus on estimands that use treatment policy, hypothetical, composite, or a combination of strategies for handling IEs, under the assumption that IEs occur independently of each other and the primary endpoint. Validation against simulation-based estimates shows strong agreement, and we explore deviations in power estimates in scenarios where outcomes and IEs are dependent. We illustrate the practical application of our approach through a case study in nasal polyposis, examining the sensitivity of sample size requirements to varying IE rates and their impacts on post-IE outcomes. The proposed formulae facilitate rapid and accurate power and assurance calculations, enabling clinical trial designs to be more closely aligned with the estimand of interest.

Problem

• intercurrent events
• estimands
• time-to-event endpoints
• statistical power
• sample size

Innovation

• estimand
• intercurrent events
• time-to-event endpoint
• power calculation
• sample size